Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9493
    Prev
    Next
    INDEX
    Explanations

    descriptions related to news events and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of suspects in a criminal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.80
    soDeliveryDate
    -0.78
    ophon
    -0.74
    itivity
    -0.73
     gears
    -0.71
    GMT
    -0.70
     Catalog
    -0.65
     conventions
    -0.64
    é¾įåĸļ士
    -0.64
    umption
    -0.63
    POSITIVE LOGITS
     whom
    0.81
     Tsarnaev
    0.71
    sov
    0.71
    emort
    0.69
     Kessler
    0.68
     unidentified
    0.67
     ENT
    0.66
    ryce
    0.66
     Kov
    0.66
     Asuka
    0.65
    Activations Density 0.552%

    No Known Activations